Vabilo na predavanje / Invitation to the Lecture

[Brigita Pirc]

VABILO NA PREDAVANJE /  INVITATION TO THE LECTURE

 

Prof. Dr. Peter Filzmoser


Dept. of  Statistics & Probability Theory, Vienna University of Technology, Wiedner Hauptstr. 8-10, A-1040 Vienna, Austria

 

Sreda / Wednesday, 1. 2. 2012, ob / at 12:15


Velika predavalnica Kemijskega inštituta / Lecture Hall at the National Institute of Chemistry; Hajdrihova 19, Ljubljana 


 

Review of Sparse Methods in Regression and Classification with Application to Chemometrics

 

 

Povzetek / Abstract

 

Sparse statistical methods lead to parameter estimates that contain exact zeros. This has advantages especially in the analysis of high-dimensional data, because the contribution of single variables - potential noise variables - is set to zero. Recent proposals for sparse methods will be reviewed in the context of regression and classification, and the performance of these methods with their non-sparse counterparts will be compared, using several data examples from chemometrics.

 

 

Vljudno vabljeni! / Kindly invited

 

 

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.ijs.si/pipermail/predavanja/attachments/20120130/70bf8e59/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Filzmoser.pdf
Type: application/octet-stream
Size: 267904 bytes
Desc: Filzmoser.pdf
URL: <http://mailman.ijs.si/pipermail/predavanja/attachments/20120130/70bf8e59/attachment.obj>